Daily data with regressors, cross_validation function errors
- Dominant language
- Python
- Stars
- 20.4k
- Forks
- 4.6k
- Avg merge
- 19h 52m
- Merged PRs (30d)
- 1
Description
Hi, I built a prophet model with regressors and wanted to use cross_validation function to evaluate the model.
Here is the code:
df.cv <- prophet::cross_validation(train_model2, horizon=180, units = 'days')
and it outputs an error message:
**Error in if (model$uncertainty.samples) { : argument is of length zero**
> str(train_model2)
'data.frame': 396 obs. of 7 variables:
$ T_TV_imp : num 17.2 17.7 18.2 18 18 ...
$ T_sem_spend: num 12.2 12.7 12.9 13 13 ...
$ T_dsp_spend: num 11.4 11.8 11.9 11.9 11.8 ...
$ T_sop_spend: num 10.4 10.9 11.2 11.5 11.6 ...
$ T_bch_spend: num 10.9 11.6 11.9 12.3 12.5 ...
$ ds : chr "2020-03-16" "2020-03-17" "2020-03-18" "2020-03-19" ...
$ y : int 7****
Could you help me understand what went wrong with the code or the training dataset?
Thanks!
Contributor guide
Assessment
This issue has not been assessed yet.